AINeutralarXiv – CS AI · May 126/10
🧠
Zero-shot Imitation Learning by Latent Topology Mapping
Researchers introduce ZALT, an imitation learning method that enables AI agents to solve unseen tasks by identifying latent hub states in demonstrated trajectories and planning over abstract topology. The approach achieves 55% zero-shot success on complex maze tasks compared to 6% for existing baselines, addressing the challenge of adapting learned behaviors to new long-horizon goals without additional training.